A novel generative model for brain tumor detection using magnetic resonance imaging
Computerized Medical Imaging and Graphics · 2025-04 · 121 · 102498
DOI: 10.1016/j.compmedimag.2025.102498 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computerized Medical Imaging and Graphics, 2025-04. Verfasst von José Jerovane da Costa Nascimento und 6 weiteren Autor:innen. Beteiligte Einrichtung: Universidade Federal do Ceará, Fortaleza, 60455-760, CE, Brazil. Electronic address: jerovane@alu.ufc.br. Hauptthemen laut MEDLINE: Brain Neoplasms, Magnetic Resonance Imaging, Deep Learning, Image Interpretation, Computer-Assisted. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 56 Literaturangaben. Gefördert von: Conselho Nacional de Desenvolvimento Científico e Tecnológico.
Abstract (Originalsprache)
Brain tumors are a disease that kills thousands of people worldwide each year. Early identification through diagnosis is essential for monitoring and treating patients. The proposed study brings a new method through intelligent computational cells that are capable of segmenting the tumor region with high precision. The method uses deep learning to detect brain tumors with the "You only look once" (Yolov8) framework, and a fine-tuning process at the end of the network layer using intelligent computational cells capable of traversing the detected region, segmenting the edges of the brain tumor. In addition, the method uses a classification pipeline that combines a set of classifiers and extractors combined with grid search, to find the best combination and the best parameters for the dataset. The method obtained satisfactory results above 98% accuracy for region detection, and above 99% for brain tumor segmentation and accuracies above 98% for binary classification of brain tumor, and segmentation time obtaining less than 1 s, surpassing the state of the art compared to the same database, demonstrating the effectiveness of the proposed method. The new approach proposes the classification of different databases through data fusion to classify the presence of tumor in MRI images, as well as the patient's life span. The segmentation and classification steps are validated by comparing them with the literature, with comparisons between works that used the same dataset. The method addresses a new generative AI for brain tumor capable of generating a pre-diagnosis through input data through Large Language Model (LLM), and can be used in systems to aid medical imaging diagnosis. As a contribution, this study employs new detection models combined with innovative methods based on digital image processing to improve segmentation metrics, as well as the use of Data Fusion, combining two tumor datasets to enhance classification performance. The study also utilizes LLM models to refine the pre-diagnosis obtained post-classification. Thus, this study proposes a Computer-Aided Diagnosis (CAD) method through AI with PDI, CNN, and LLM.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Universidade Federal do Ceará, Fortaleza, 60455-760, CE, Brazil. Electronic address: jerovane@alu.ufc.br.
- Instituto Federal de Educação, Ciência e Tecnologia do Ceará - Campus Fortaleza, Fortaleza, 60040-531, CE, Brazil. Electronic address: adriell.gomes.marques07@aluno.ifce.edu.br.
- Universidade Federal do Cariri, Juazeiro do Norte, 63048-080, CE, Brazil. Electronic address: lucas.nascimento@aluno.ufca.edu.br.
- Instituto Federal de Educação, Ciência e Tecnologia do Ceará - Campus Fortaleza, Fortaleza, 60040-531, CE, Brazil. Electronic address: mauriciodourado@ifce.edu.br.
- Universidade da Integração Internacional da Lusofonia Afro-Brasileira, Redenção, 43900-000, CE, Brazil. Electronic address: carlosbarros@unilab.edu.br.
- Universidade Federal do Ceará, Fortaleza, 60455-760, CE, Brazil. Electronic address: victor.albuquerque@ieee.org.
Förderung
- Conselho Nacional de Desenvolvimento Científico e Tecnológico
Zitieren
APA
da Costa Nascimento, J. J., Marques, A. G., do Nascimento Souza, L., de Mattos Dourado Junior, C. M. J., da Silva Barros, A. C., de Albuquerque, V. H. C., & de Freitas Sousa, L. F. (2025). A novel generative model for brain tumor detection using magnetic resonance imaging. Computerized Medical Imaging and Graphics, 121, 102498. https://doi.org/10.1016/j.compmedimag.2025.102498
Vancouver
da Costa Nascimento JJ, Marques AG, do Nascimento Souza L, de Mattos Dourado Junior CMJ, da Silva Barros AC, de Albuquerque VHC, et al. A novel generative model for brain tumor detection using magnetic resonance imaging. Computerized Medical Imaging and Graphics. 2025;121:102498. doi:10.1016/j.compmedimag.2025.102498
BibTeX
@article{daCostaNascimento2025,
author = {da Costa Nascimento, José Jerovane and Marques, Adriell Gomes and do Nascimento Souza, Lucas and de Mattos Dourado Junior, Carlos Mauricio Jaborandy and da Silva Barros, Antonio Carlos and de Albuquerque, Victor Hugo C and de Freitas Sousa, Luís Fabrício},
title = {A novel generative model for brain tumor detection using magnetic resonance imaging},
journal = {Computerized Medical Imaging and Graphics},
year = {2025},
volume = {121},
pages = {102498},
doi = {10.1016/j.compmedimag.2025.102498}
}
EUVIMED